How to Use the ArcGIS MCP in Pydantic AI

Type-safe spatial operations for Pydantic AI with the ArcGIS MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ArcGIS MCP to Pydantic AI

Create your Vinkius account to connect ArcGIS to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup ArcGIS with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validated spatial data for Pydantic AI

Ensure every response from the server matches your expected schema. By using Pydantic AI, you force the agent to validate coordinates and route data against your defined models at runtime. If the `calculate_od_matrix` tool returns unexpected data types, the agent errors out immediately. This stops bad data from propagating through your system.

Route solving with Pydantic AI

Call `solve_nav_route` to get turn-by-turn directions that satisfy your strict type requirements. You define the input point sequence as a structured list, and the server returns the path. Your agent handles the result inside a standard Pydantic model. It's the most reliable way to integrate map data into a type-checked application.

Reverse geocoding in Pydantic AI

Turn coordinates into addresses using `reverse_geocode`. Your agent sends the lon,lat pair, and you get back a validated address object that your application code can trust. This workflow prevents runtime crashes caused by unexpected API responses. You define the structure, and the framework enforces it on every tool call.

Setup guide

Set up ArcGIS MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "arcgis-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to ArcGIS tools.",
)

result = await agent.run("List recent ArcGIS transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by ArcGIS. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect ArcGIS now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about ArcGIS MCP in Pydantic AI

Install the necessary dependencies and initialize an MCPToolset with the server's URL. You then pass this toolset to your Agent instance to enable the spatial capabilities.

Yes, it validates every response against your Pydantic models. If the server returns fields that don't match your schema, the agent will throw a validation error.

The server supports SSE and Streamable HTTP. You pick the transport that fits your environment, and the toolset handles the connection.

Your Pydantic model will reject the payload if it doesn't meet your structural requirements. This prevents silent corruption of your location records.

Your data is processed through an isolated, ephemeral sandbox that never stores your spatial inputs. The system validates the data in memory and discards it as soon as the agent task finishes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript